Aldo Pacchiano

papers

739

total citations

papers (22)

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

NEURIPS 2022arXiv

citations

Tactical Optimism and Pessimism for Deep Reinforcement Learning

NEURIPS 2021arXiv

citations

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

NEURIPS 2021arXiv

citations

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

NEURIPS 2020arXiv

citations

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

NEURIPS 2021arXiv

citations

Language Model Personalization via Reward Factorization

COLM 2025arXiv

citations

Learning General World Models in a Handful of Reward-Free Deployments

NEURIPS 2022arXiv

citations

Best of Both Worlds Model Selection

NEURIPS 2022arXiv

citations

Improving Offline RL by Blending Heuristics

ICLR 2024arXiv

citations

Neural Pseudo-Label Optimism for the Bank Loan Problem

NEURIPS 2021arXiv

citations

Anytime Model Selection in Linear Bandits

NEURIPS 2023arXiv

citations

Second Order Bounds for Contextual Bandits with Function Approximation

ICLR 2025arXiv

citations

Experiment Planning with Function Approximation

NEURIPS 2023arXiv

citations

Near Optimal Policy Optimization via REPS

NEURIPS 2021arXiv

citations

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation

ICML 2025arXiv

citations

Multiple-policy Evaluation via Density Estimation

ICML 2025arXiv

citations

A Unified Model and Dimension for Interactive Estimation

NEURIPS 2023arXiv

citations

Provable Interactive Learning with Hindsight Instruction Feedback

ICML 2024arXiv

citations

Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward

NEURIPS 2025arXiv

citations

Aldo Pacchiano

papers (22)

Effective Diversity in Population Based Reinforcement Learning

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Model Selection in Contextual Stochastic Bandit Problems

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

Tactical Optimism and Pessimism for Deep Reinforcement Learning

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

Language Model Personalization via Reward Factorization

Learning General World Models in a Handful of Reward-Free Deployments

Best of Both Worlds Model Selection

Improving Offline RL by Blending Heuristics

Neural Pseudo-Label Optimism for the Bank Loan Problem

Anytime Model Selection in Linear Bandits

Second Order Bounds for Contextual Bandits with Function Approximation

Experiment Planning with Function Approximation

Near Optimal Policy Optimization via REPS

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation

Multiple-policy Evaluation via Density Estimation

A Unified Model and Dimension for Interactive Estimation

Provable Interactive Learning with Hindsight Instruction Feedback

Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward

papers (22)

Effective Diversity in Population Based Reinforcement Learning

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Model Selection in Contextual Stochastic Bandit Problems

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

Tactical Optimism and Pessimism for Deep Reinforcement Learning

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

Language Model Personalization via Reward Factorization

Learning General World Models in a Handful of Reward-Free Deployments

Best of Both Worlds Model Selection

Improving Offline RL by Blending Heuristics

Neural Pseudo-Label Optimism for the Bank Loan Problem

Anytime Model Selection in Linear Bandits

Second Order Bounds for Contextual Bandits with Function Approximation

Experiment Planning with Function Approximation

Near Optimal Policy Optimization via REPS

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation

Multiple-policy Evaluation via Density Estimation

A Unified Model and Dimension for Interactive Estimation

Provable Interactive Learning with Hindsight Instruction Feedback

Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward